DEVOPSdigest

Pulumi now offers native ways to manage Pinecone indexes, including its latest serverless indexes.

Pinecone is a serverless vector database with an easy-to-use API that allows developers to build and deploy high-performance AI applications. This is incredibly important as applications involving large language models, generative AI, and semantic search require a vector database to store and retrieve vector embeddings.

Pulumi also now has a template to launch and run LangChain’s LangServe in Amazon ECS, a container management service. This in addition to Pulumi’s existing support in running Next.js frontend applications in Vercel, managing Apache Spark clusters in Databricks and 150+ other cloud and SaaS services.

The GenAI tech stack is new and emerging but has typically consisted of a LLM service and a vector data store. Running this stack on a laptop is fairly simple but getting it to production is far harder. Most of this is done manually through a CLI or a web console, which introduces manual errors and repeatability problems that affect the security and reliability of the product.

Pulumi has made it easy to take a GenAI stack running locally and get it in production in the cloud with Pulumi AI, the fastest way to learn and build Infrastructure as Code (IaC). As GenAI complexity actually relates to cloud infrastructure provisioning and management, Pulumi is purpose built to manage this cloud complexity and is easy to use to support a new use case of AI.

Pulumi allows developers to tie together all the different pieces of infrastructure that goes into their GenAI product and manage it from a simple Python program.